NODE IK: Solving Inverse Kinematics with Neural Ordinary Differential Equations for Path Planning

TL;DR

This paper introduces NODE IK, a neural ODE-based inverse kinematics solver that enhances accuracy and efficiency for robotic path planning, leveraging continuous dynamics to outperform traditional data-driven methods.

Contribution

The paper presents a novel IK solver using Neural ODEs, improving accuracy and memory efficiency over existing data-driven approaches.

Findings

Outperforms existing data-driven IK methods in accuracy

Requires less training time and memory

Effective across multiple robotic systems

Abstract

This paper proposes a novel inverse kinematics (IK) solver of articulated robotic systems for path planning. IK is a traditional but essential problem for robot manipulation. Recently, data-driven methods have been proposed to quickly solve the IK for path planning. These methods can handle a large amount of IK requests at once with the advantage of GPUs. However, the accuracy is still low, and the model requires considerable time for training. Therefore, we propose an IK solver that improves accuracy and memory efficiency by utilizing the continuous hidden dynamics of Neural ODE. The performance is compared using multiple robots.